db-conn-mcp

Overview Schema Source Related Servers Discussions Admin

find_columns

Locate columns by name across all database tables using fuzzy, case-insensitive substring matching, then cap broad results with a limit before querying.

Instructions

Find columns by name across all tables (fuzzy, case-insensitive substring).

e.g. pattern "email" matches user_email, EMAIL_ADDRESS. Use this to locate where a concept lives before querying. limit returns at most that many rows — set it when a broad pattern would otherwise match half the database.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "database": "<database>",
      "pattern": "<pattern>"
    },
    "name": "find_columns"
  }
}

Input Schema

Name	Required	Description	Default
`limit`	No
`pattern`	Yes
`database`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does disclose the matching semantics (fuzzy, case-insensitive substring), the search scope (all tables), and the row-capping behavior of `limit` including the risk of overly broad matches. It does not discuss whether the default null limit means unlimited, or any performance caveat about scanning every table.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the core definition, then adds one illustrative example and one tuning tip, each of which earns its place. Slightly long for a three-parameter lookup, but no sentence is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return shape need not be described, and the description covers the discovery role, matching behavior, and result capping. The one loose end is the null default for `limit`, which an agent must infer as unbounded.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate, and it does for two of three parameters: `pattern` gets matching semantics plus worked examples, and `limit` gets both its meaning and tuning advice. The required `database` parameter is left entirely implicit, which keeps this from a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Find columns by name across all tables") and immediately qualifies the matching rule as fuzzy, case-insensitive substring, with concrete examples ("email" matches user_email, EMAIL_ADDRESS). This distinguishes it from value-search siblings like search_value and from schema-dumping tools, which return structure rather than a name match.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use guidance: "Use this to locate where a concept lives before querying," which frames it as a discovery step preceding execute_read_query. It also advises setting `limit` for broad patterns. It stops short of naming a when-not case or pointing at a specific alternative when the exact table is already known.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

This server cannot be deployed